© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9171
    Prev
    Next
    INDEX
    Explanations

    systems and platforms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     се
    0.49
     для
    0.48
    [
    0.48
     sk
    0.47
     katika
    0.47
     για
    0.47
     sa
    0.47
     este
    0.46
     в
    0.46
     se
    0.46
    POSITIVE LOGITS
    ጷ
    0.59
     Mathematical
    0.55
    ImageQueue
    0.54
     LongNumber
    0.54
     (’
    0.54
    🌝
    0.54
     nineteen
    0.53
     Archaeology
    0.53
     unrivalled
    0.53
    ୈ
    0.53
    Activations Density 0.085%

    No Known Activations